def main(args):
network = importlib.import_module(args.model_def)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(
log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir,
'arguments.txt'))
# Store some git revision info in a text file in the log directory
# src_path,_ = os.path.split(os.path.realpath(__file__))
# facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
# Fetch dataets
# VGGface2
print('Fetch VGGface2 as source dataset at {}'.format(
args.vggface2_train_dir))
src_train_set = facenet.get_dataset(args.vggface2_train_dir)
# validation_set = facenet.get_dataset(args.vggface2_val_dir)
# COX S2V
print('Fetch COX-S2V as target dataset at {}'.format(args.cox_video_dir))
cox_dataset = cox.cox_data(args.cox_still_dir, args.cox_video_dir,
args.cox_pairs)
train_folds = [0, 1, 2]
evaluation_folds = [3, 4, 5, 6, 7, 8, 9]
# cox_train_list = cox_dataset.get_dataset(train_folds)
# cox_val_list = list(itertools.chain.from_iterable(fold_list[3:10]))
tgt_train_set = cox_dataset.get_dataset(train_folds, video_only=True)
# tgt_val_set = cox.get_video_dataset(args.cox_video_dir, cox_val_list)
cox_paths, cox_issame = cox_dataset.get_pairs(evaluation_folds)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
if args.pretrained_model:
print('Pre-trained model: %s' %
os.path.expanduser(args.pretrained_model))
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(
os.path.expanduser(args.lfw_dir), pairs)
# Get the paths for embeddings projection
# Get the paths for embeddings projection
lfw_proj_paths, lfw_proj_labels = lfw.get_paths_from_file(
args.lfw_dir, args.lfw_projection)
cox_proj_paths, cox_proj_labels = cox_dataset.get_paths_from_file(
args.cox_projection)
# Combine projection paths
projection_paths = lfw_proj_paths + cox_proj_paths
proj_labels = lfw_proj_labels + cox_proj_labels
# Create label map if does not exist
metadata_filename = 'meta.tsv'
emb_dir = os.path.join(os.path.expanduser(log_dir), 'emb')
if not os.path.isdir(
emb_dir): # Create the log directory if it doesn't exist
os.makedirs(emb_dir)
with open(os.path.join(emb_dir, metadata_filename), "w") as meta_file:
csvWriter = csv.writer(meta_file, delimiter='\t')
csvWriter.writerows(np.array([proj_labels]).T)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32,
name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string,
shape=(None, 4),
name='image_paths')
labels_placeholder = tf.placeholder(tf.int64,
shape=(None, 4),
name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(4, ), (4, )],
shared_name=None,
name=None)
enqueue_op = input_queue.enqueue_many(
[image_paths_placeholder, labels_placeholder])
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unstack(filenames):
file_contents = tf.read_file(filename)
image = tf.image.decode_image(file_contents, channels=3)
if args.random_crop:
image = tf.random_crop(
image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(
image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
image_batch, labels_batch = tf.train.batch_join(
images_and_labels,
batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()],
enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
labels_batch = tf.identity(labels_batch, 'label_batch')
# Build the inference graph
prelogits, _ = network.inference(
image_batch,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Split embeddings into anchor, positive and negative and calculate triplet loss
anchor, positive, negative, target = tf.unstack(
tf.reshape(embeddings, [-1, 4, args.embedding_size]), 4, 1)
loss, adv_loss, triplet_loss = adversarialloss.quadruplets_loss(
anchor, positive, negative, target, args.alpha, args.lamb,
args.zeta)
# triplet_loss = tripletloss.triplet_loss(anchor, positive, negative, args.alpha)
# adv_loss = adversarialloss.adversarial_loss(anchor, target, args.alpha)
learning_rate = tf.train.exponential_decay(
learning_rate_placeholder,
global_step,
args.learning_rate_decay_epochs * args.epoch_size,
args.learning_rate_decay_factor,
staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([loss] + regularization_losses,
name='total_loss')
reg_loss = tf.add_n(regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay,
tf.global_variables())
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
# summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# Initialize variables
sess.run(tf.global_variables_initializer(),
feed_dict={phase_train_placeholder: True})
sess.run(tf.local_variables_initializer(),
feed_dict={phase_train_placeholder: True})
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if args.pretrained_model:
print('Restoring pretrained model: %s' % args.pretrained_model)
saver.restore(sess, os.path.expanduser(args.pretrained_model))
# Training and validation loop
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# save_embeddings(sess, projection_paths, epoch, embeddings, labels_batch, image_paths_placeholder,
# labels_placeholder,
# batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op,
# args.batch_size, emb_dir, args.embedding_size, tag='lfw')
#
# # Evaluate on COX
# evaluate(sess, cox_paths, embeddings, labels_batch, image_paths_placeholder,
# labels_placeholder,
# batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder,
# enqueue_op,
# cox_issame, args.batch_size,
# args.lfw_nrof_folds, log_dir, step, summary_writer, args.embedding_size,
# tag='cox')
#
# if args.lfw_dir:
# evaluate(sess, lfw_paths, embeddings, labels_batch, image_paths_placeholder, labels_placeholder,
# batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op, actual_issame, args.batch_size,
# args.lfw_nrof_folds, log_dir, step, summary_writer, args.embedding_size)
# Train for one epoch
train(args, sess, src_train_set, tgt_train_set, epoch,
image_paths_placeholder, labels_placeholder,
labels_batch, batch_size_placeholder,
learning_rate_placeholder, phase_train_placeholder,
enqueue_op, input_queue, global_step, embeddings,
total_loss, triplet_loss, adv_loss, reg_loss, train_op,
summary_writer, args.learning_rate_schedule_file,
args.embedding_size)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer,
model_dir, subdir, step)
# Evaluate on LFW
return model_dir
def main(args):
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs)
result_dir = '../data/'
plt.ioff() # Disable interactive plotting mode
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
print('Loading model "%s"' % args.model_file)
facenet.load_model(args.model_file)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
image_size = int(images_placeholder.get_shape()[1])
# Run test on LFW to check accuracy for different horizontal/vertical translations of input images
if args.nrof_offsets>0:
step = 3
offsets = np.asarray([x*step for x in range(-args.nrof_offsets//2+1, args.nrof_offsets//2+1)])
horizontal_offset_accuracy = [None] * len(offsets)
for idx, offset in enumerate(offsets):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, translate_images, (offset,0), 60, args.orig_image_size, args.seed)
print('Hoffset: %1.3f Accuracy: %1.3f+-%1.3f' % (offset, np.mean(accuracy), np.std(accuracy)))
horizontal_offset_accuracy[idx] = np.mean(accuracy)
vertical_offset_accuracy = [None] * len(offsets)
for idx, offset in enumerate(offsets):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, translate_images, (0,offset), 60, args.orig_image_size, args.seed)
print('Voffset: %1.3f Accuracy: %1.3f+-%1.3f' % (offset, np.mean(accuracy), np.std(accuracy)))
vertical_offset_accuracy[idx] = np.mean(accuracy)
fig = plt.figure(1)
plt.plot(offsets, horizontal_offset_accuracy, label='Horizontal')
plt.plot(offsets, vertical_offset_accuracy, label='Vertical')
plt.legend()
plt.grid(True)
plt.title('Translation invariance on LFW')
plt.xlabel('Offset [pixels]')
plt.ylabel('Accuracy')
# plt.show()
print('Saving results in %s' % result_dir)
fig.savefig(os.path.join(result_dir, 'invariance_translation.png'))
save_result(offsets, horizontal_offset_accuracy, os.path.join(result_dir, 'invariance_translation_horizontal.txt'))
save_result(offsets, vertical_offset_accuracy, os.path.join(result_dir, 'invariance_translation_vertical.txt'))
# Run test on LFW to check accuracy for different rotation of input images
if args.nrof_angles>0:
step = 3
angles = np.asarray([x*step for x in range(-args.nrof_offsets//2+1, args.nrof_offsets//2+1)])
rotation_accuracy = [None] * len(angles)
for idx, angle in enumerate(angles):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, rotate_images, angle, 60, args.orig_image_size, args.seed)
print('Angle: %1.3f Accuracy: %1.3f+-%1.3f' % (angle, np.mean(accuracy), np.std(accuracy)))
rotation_accuracy[idx] = np.mean(accuracy)
fig = plt.figure(2)
plt.plot(angles, rotation_accuracy)
plt.grid(True)
plt.title('Rotation invariance on LFW')
plt.xlabel('Angle [deg]')
plt.ylabel('Accuracy')
# plt.show()
print('Saving results in %s' % result_dir)
fig.savefig(os.path.join(result_dir, 'invariance_rotation.png'))
save_result(angles, rotation_accuracy, os.path.join(result_dir, 'invariance_rotation.txt'))
# Run test on LFW to check accuracy for different scaling of input images
if args.nrof_scales>0:
step = 0.05
scales = np.asarray([x*step+1 for x in range(-args.nrof_offsets//2+1, args.nrof_offsets//2+1)])
scale_accuracy = [None] * len(scales)
for scale_idx, scale in enumerate(scales):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, scale_images, scale, 60, args.orig_image_size, args.seed)
print('Scale: %1.3f Accuracy: %1.3f+-%1.3f' % (scale, np.mean(accuracy), np.std(accuracy)))
scale_accuracy[scale_idx] = np.mean(accuracy)
fig = plt.figure(3)
plt.plot(scales, scale_accuracy)
plt.grid(True)
plt.title('Scale invariance on LFW')
plt.xlabel('Scale')
plt.ylabel('Accuracy')
# plt.show()
print('Saving results in %s' % result_dir)
fig.savefig(os.path.join(result_dir, 'invariance_scale.png'))
save_result(scales, scale_accuracy, os.path.join(result_dir, 'invariance_scale.txt'))
def main(args):
network = importlib.import_module(args.model_def)
image_size = (args.image_size, args.image_size)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(
log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
stat_file_name = os.path.join(log_dir, 'stat.h5')
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir,
'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
random.seed(args.seed)
dataset = facenet.get_dataset(args.data_dir)
if args.filter_filename:
dataset = filter_dataset(dataset,
os.path.expanduser(args.filter_filename),
args.filter_percentile,
args.filter_min_nrof_images_per_class)
if args.validation_set_split_ratio > 0.0:
train_set, val_set = facenet.split_dataset(
dataset, args.validation_set_split_ratio,
args.min_nrof_val_images_per_class, 'SPLIT_IMAGES')
else:
train_set, val_set = dataset, []
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(
os.path.expanduser(args.lfw_dir), pairs)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list) > 0, 'The training set should not be empty'
val_image_list, val_label_list = facenet.get_image_paths_and_labels(
val_set)
# Create a queue that produces indices into the image_list and label_list
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
index_queue = tf.train.range_input_producer(range_size,
num_epochs=None,
shuffle=True,
seed=None,
capacity=32)
index_dequeue_op = index_queue.dequeue_many(
args.batch_size * args.epoch_size, 'index_dequeue')
learning_rate_placeholder = tf.placeholder(tf.float32,
name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string,
shape=(None, 1),
name='image_paths')
labels_placeholder = tf.placeholder(tf.int32,
shape=(None, 1),
name='labels')
control_placeholder = tf.placeholder(tf.int32,
shape=(None, 1),
name='control')
nrof_preprocess_threads = 4
input_queue = data_flow_ops.FIFOQueue(
capacity=2000000,
dtypes=[tf.string, tf.int32, tf.int32],
shapes=[(1, ), (1, ), (1, )],
shared_name=None,
name=None)
enqueue_op = input_queue.enqueue_many(
[image_paths_placeholder, labels_placeholder, control_placeholder],
name='enqueue_op')
image_batch, label_batch = facenet.create_input_pipeline(
input_queue, image_size, nrof_preprocess_threads,
batch_size_placeholder)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
label_batch = tf.identity(label_batch, 'label_batch')
print('Number of classes in training set: %d' % nrof_classes)
print('Number of examples in training set: %d' % len(image_list))
print('Number of classes in validation set: %d' % len(val_set))
print('Number of examples in validation set: %d' % len(val_image_list))
print('Building training graph')
# Build the inference graph
prelogits, _ = network.inference(
image_batch,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
logits = slim.fully_connected(
prelogits,
len(train_set),
activation_fn=None,
weights_initializer=slim.initializers.xavier_initializer(),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits',
reuse=False)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Norm for the prelogits
eps = 1e-4
prelogits_norm = tf.reduce_mean(
tf.norm(tf.abs(prelogits) + eps, ord=args.prelogits_norm_p,
axis=1))
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES,
prelogits_norm * args.prelogits_norm_loss_factor)
# Add center loss
prelogits_center_loss, _ = facenet.center_loss(prelogits, label_batch,
args.center_loss_alfa,
nrof_classes)
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES,
prelogits_center_loss * args.center_loss_factor)
learning_rate = tf.train.exponential_decay(
learning_rate_placeholder,
global_step,
args.learning_rate_decay_epochs * args.epoch_size,
args.learning_rate_decay_factor,
staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch,
logits=logits,
name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy,
name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
correct_prediction = tf.cast(
tf.equal(tf.argmax(logits, 1), tf.cast(label_batch, tf.int64)),
tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
# Calculate the total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses,
name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay,
tf.global_variables(), args.log_histograms)
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
print('Running training')
nrof_steps = args.max_nrof_epochs * args.epoch_size
nrof_val_samples = int(
math.ceil(args.max_nrof_epochs / args.validate_every_n_epochs)
) # Validate every validate_every_n_epochs as well as in the last epoch
stat = {
'loss':
np.zeros((nrof_steps, ), np.float32),
'center_loss':
np.zeros((nrof_steps, ), np.float32),
'reg_loss':
np.zeros((nrof_steps, ), np.float32),
'xent_loss':
np.zeros((nrof_steps, ), np.float32),
'prelogits_norm':
np.zeros((nrof_steps, ), np.float32),
'accuracy':
np.zeros((nrof_steps, ), np.float32),
'val_loss':
np.zeros((nrof_val_samples, ), np.float32),
'val_xent_loss':
np.zeros((nrof_val_samples, ), np.float32),
'val_accuracy':
np.zeros((nrof_val_samples, ), np.float32),
'lfw_accuracy':
np.zeros((args.max_nrof_epochs, ), np.float32),
'lfw_valrate':
np.zeros((args.max_nrof_epochs, ), np.float32),
'learning_rate':
np.zeros((args.max_nrof_epochs, ), np.float32),
'time_train':
np.zeros((args.max_nrof_epochs, ), np.float32),
'time_validate':
np.zeros((args.max_nrof_epochs, ), np.float32),
'time_evaluate':
np.zeros((args.max_nrof_epochs, ), np.float32),
'prelogits_hist':
np.zeros((args.max_nrof_epochs, 1000), np.float32),
}
for epoch in range(1, args.max_nrof_epochs + 1):
step = sess.run(global_step, feed_dict=None)
# Train for one epoch
t = time.time()
cont = train(
args, sess, epoch, image_list, label_list,
index_dequeue_op, enqueue_op, image_paths_placeholder,
labels_placeholder, learning_rate_placeholder,
phase_train_placeholder, batch_size_placeholder,
control_placeholder, global_step, total_loss, train_op,
summary_op, summary_writer, regularization_losses,
args.learning_rate_schedule_file, stat, cross_entropy_mean,
accuracy, learning_rate, prelogits, prelogits_center_loss,
args.random_rotate, args.random_crop, args.random_flip,
prelogits_norm, args.prelogits_hist_max,
args.use_fixed_image_standardization)
stat['time_train'][epoch - 1] = time.time() - t
if not cont:
break
t = time.time()
if len(val_image_list) > 0 and (
(epoch - 1) % args.validate_every_n_epochs
== args.validate_every_n_epochs - 1
or epoch == args.max_nrof_epochs):
validate(args, sess, epoch, val_image_list, val_label_list,
enqueue_op, image_paths_placeholder,
labels_placeholder, control_placeholder,
phase_train_placeholder, batch_size_placeholder,
stat, total_loss, regularization_losses,
cross_entropy_mean, accuracy,
args.validate_every_n_epochs,
args.use_fixed_image_standardization)
stat['time_validate'][epoch - 1] = time.time() - t
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer,
model_dir, subdir, epoch)
# Evaluate on LFW
t = time.time()
if args.lfw_dir:
evaluate(sess, enqueue_op, image_paths_placeholder,
labels_placeholder, phase_train_placeholder,
batch_size_placeholder, control_placeholder,
embeddings, label_batch, lfw_paths, actual_issame,
args.lfw_batch_size, args.lfw_nrof_folds, log_dir,
step, summary_writer, stat, epoch,
args.lfw_distance_metric, args.lfw_subtract_mean,
args.lfw_use_flipped_images,
args.use_fixed_image_standardization)
stat['time_evaluate'][epoch - 1] = time.time() - t
print('Saving statistics')
with h5py.File(stat_file_name, 'w') as f:
for key, value in stat.iteritems():
f.create_dataset(key, data=value)
return model_dir
def main(args):
config = config_reader.triplets_afix_config(args.config)
np.random.seed(seed=config.seed)
network = importlib.import_module(config.model_def)
chokepoint_dataset = chokepoint.chokepoint_data(config.chokepoint_still_dir,
config.chokepoint_video_dir,
config.chokepoint_pairs)
fold_list = [([0, 1], [2, 3, 4]),
([1, 2], [3, 4, 0]),
([2, 3], [4, 0, 1]),
([3, 4], [0, 1, 2]),
([4, 0], [1, 2, 3])]
for fold_idx in range(5):
print('Fold: {}'.format(fold_idx))
train_folds, evaluation_folds = fold_list[fold_idx]
# Train set
chokepoint_train_set = chokepoint_dataset.get_S2V_dataset(train_folds)
chokepoint1_paths, chokepoint1_issame = chokepoint_dataset.get_pairs(train_folds)
# Validation set
chokepoint2_paths, chokepoint2_issame = chokepoint_dataset.get_pairs(evaluation_folds)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), 'fold{}_'.format(fold_idx) + subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), 'fold{}_'.format(fold_idx) + subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir, 'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
if args.pretrained_model:
print('Pre-trained model: %s' % os.path.expanduser(args.pretrained_model))
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, lfw_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,3), name='image_paths')
labels_placeholder = tf.placeholder(tf.int64, shape=(None,3), name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(3,), (3,)],
shared_name=None, name=None)
enqueue_op = input_queue.enqueue_many([image_paths_placeholder, labels_placeholder])
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unstack(filenames):
file_contents = tf.read_file(filename)
image = tf.image.decode_image(file_contents, channels=3)
if args.random_crop:
image = tf.random_crop(image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
image_batch, labels_batch = tf.train.batch_join(
images_and_labels, batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()], enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
labels_batch = tf.identity(labels_batch, 'label_batch')
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Split embeddings into anchor, positive and negative and calculate triplet loss
anchor, positive, negative = tf.unstack(tf.reshape(embeddings, [-1,3,args.embedding_size]), 3, 1)
triplet_loss = facenet.triplet_loss(anchor, positive, negative, args.alpha)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([triplet_loss] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, tf.global_variables())
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
# summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# Initialize variables
sess.run(tf.global_variables_initializer(), feed_dict={phase_train_placeholder:True})
sess.run(tf.local_variables_initializer(), feed_dict={phase_train_placeholder:True})
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if args.pretrained_model:
print('Restoring pretrained model: %s' % args.pretrained_model)
saver.restore(sess, os.path.expanduser(args.pretrained_model))
# Training and validation loop
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Evaluate on COX
evaluate(sess, chokepoint1_paths, embeddings, labels_batch, image_paths_placeholder,
labels_placeholder,
batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op,
chokepoint1_issame, 100,
2, log_dir, step, summary_writer, args.embedding_size,
tag='chokepoint_train')
evaluate(sess, chokepoint2_paths, embeddings, labels_batch, image_paths_placeholder, labels_placeholder,
batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op,
chokepoint2_issame, 100,
3, log_dir, step, summary_writer, args.embedding_size, tag='chokepoint_eval')
# Evaluate on LFW
# if args.lfw_dir:
# lfw_result = evaluate(sess, lfw_paths, embeddings, labels_batch, image_paths_placeholder, labels_placeholder,
# batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op,
# lfw_issame, args.batch_size,
# args.lfw_nrof_folds, log_dir, step, summary_writer, args.embedding_size, tag='lfw')
# Train for one epoch
train(args, sess, chokepoint_train_set, epoch, image_paths_placeholder, labels_placeholder, labels_batch,
batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op, input_queue, global_step,
embeddings, total_loss, train_op, summary_writer, args.learning_rate_schedule_file,
args.embedding_size)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step)
return model_dir
def main(args):
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs)
# Get the paths for embeddings projection
lfw_proj_paths, lfw_proj_labels = lfw.get_paths_from_file(args.lfw_dir, args.lfw_projection)
# Create label map if does not exist
if not os.path.exists(args.emb_dir):
os.makedirs(args.emb_dir)
with open(os.path.join(args.emb_dir, 'meta.tsv'), "w") as meta_file:
csvWriter = csv.writer(meta_file, delimiter='\t')
csvWriter.writerows(np.array([lfw_proj_labels]).T)
with tf.Graph().as_default():
with tf.Session() as sess:
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,1), name='image_paths')
labels_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='labels')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
control_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='control')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
nrof_preprocess_threads = 4
image_size = (args.image_size, args.image_size)
eval_input_queue = data_flow_ops.FIFOQueue(capacity=2000000,
dtypes=[tf.string, tf.int32, tf.int32],
shapes=[(1,), (1,), (1,)],
shared_name=None, name=None)
eval_enqueue_op = eval_input_queue.enqueue_many([image_paths_placeholder, labels_placeholder, control_placeholder], name='eval_enqueue_op')
image_batch, label_batch = facenet.create_input_pipeline(eval_input_queue, image_size, nrof_preprocess_threads, batch_size_placeholder)
# Load the model
input_map = {'image_batch': image_batch, 'label_batch': label_batch, 'phase_train': phase_train_placeholder}
facenet.load_model(args.model, input_map=input_map)
# Get output tensor
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
#
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
save_embeddings(sess,
lfw_proj_paths,
label_batch,
embeddings,
image_paths_placeholder,
labels_placeholder,
batch_size_placeholder,
control_placeholder,
phase_train_placeholder,
eval_enqueue_op,
args.emb_dir)
evaluate(sess, eval_enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
embeddings, label_batch, paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, args.distance_metric, args.subtract_mean,
args.use_flipped_images, args.use_fixed_image_standardization)